Skip to main content
Glama

RyanNg

by campfirein

Cipher

Overview

Cipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS's Kiro, VS Code, and Roo Code through MCP, and coding agents, such as Kimi K2. (see more on examples)

Built by Byterover team

Key Features:

  • 🔌 MCP integration with any IDE you want.
  • 🧠 Auto-generate AI coding memories that scale with your codebase.
  • 🔄 Switch seamlessly between IDEs without losing memory and context.
  • 🤝 Easily share coding memories across your dev team in real time.
  • 🧬 Dual Memory Layer that captures System 1 (Programming Concepts & Business Logic & Past Interaction) and System 2 (reasoning steps of the model when generating code).
  • ⚙️ Install on your IDE with zero configuration needed.

Quick Start 🚀

# Install globally npm install -g @byterover/cipher # Or install locally in your project npm install @byterover/cipher

Docker

# Clone and setup git clone https://github.com/campfirein/cipher.git cd cipher # Configure environment cp .env.example .env # Edit .env with your API keys # Start with Docker docker-compose up --build -d # Test curl http://localhost:3000/health

💡 Note: Docker builds automatically skip the UI build step to avoid ARM64 compatibility issues with lightningcss. The UI is not included in the Docker image by default.

To include the UI in the Docker build, use: docker build --build-arg BUILD_UI=true .

From Source

pnpm i && pnpm run build && npm link

CLI Usage 💻

# Interactive mode cipher # One-shot command cipher "Add this to memory as common causes of 'CORS error' in local dev with Vite + Express." # API server mode cipher --mode api # MCP server mode cipher --mode mcp # Web UI mode cipher --mode ui

⚠️ Note: When running MCP mode in terminal/shell, export all environment variables as Cipher won't read from .env file.

💡 Tip: CLI mode automatically continues or creates the "default" session. Use /session new <session-name> to start a fresh session.

Cipher Web UI

The Cipher Web UI provides an intuitive interface for interacting with memory-powered AI agents, featuring session management, tool integration, and real-time chat capabilities.

Configuration

Cipher supports multiple configuration options for different deployment scenarios. The main configuration file is located at memAgent/cipher.yml.

Basic Configuration ⚙️

# LLM Configuration llm: provider: openai # openai, anthropic, openrouter, ollama, qwen model: gpt-4-turbo apiKey: $OPENAI_API_KEY # System Prompt systemPrompt: 'You are a helpful AI assistant with memory capabilities.' # MCP Servers (optional) mcpServers: filesystem: type: stdio command: npx args: ['-y', '@modelcontextprotocol/server-filesystem', '.']

📖 See Configuration Guide for complete details.

Environment Variables 🔐

Create a .env file in your project root with these essential variables:

# ==================== # API Keys (At least one required) # ==================== OPENAI_API_KEY=sk-your-openai-api-key ANTHROPIC_API_KEY=sk-ant-your-anthropic-key GEMINI_API_KEY=your-gemini-api-key QWEN_API_KEY=your-qwen-api-key # ==================== # Vector Store (Optional - defaults to in-memory) # ==================== VECTOR_STORE_TYPE=qdrant # qdrant, milvus, or in-memory VECTOR_STORE_URL=https://your-cluster.qdrant.io VECTOR_STORE_API_KEY=your-qdrant-api-key # ==================== # Chat History (Optional - defaults to SQLite) # ==================== CIPHER_PG_URL=postgresql://user:pass@localhost:5432/cipher_db # ==================== # Workspace Memory (Optional) # ==================== USE_WORKSPACE_MEMORY=true WORKSPACE_VECTOR_STORE_COLLECTION=workspace_memory # ==================== # AWS Bedrock (Optional) # ==================== AWS_ACCESS_KEY_ID=your-aws-access-key AWS_SECRET_ACCESS_KEY=your-aws-secret-key AWS_DEFAULT_REGION=us-east-1 # ==================== # Advanced Options (Optional) # ==================== # Logging and debugging CIPHER_LOG_LEVEL=info # error, warn, info, debug, silly REDACT_SECRETS=true # Vector store configuration VECTOR_STORE_DIMENSION=1536 VECTOR_STORE_DISTANCE=Cosine # Cosine, Euclidean, Dot, Manhattan VECTOR_STORE_MAX_VECTORS=10000 # Memory search configuration SEARCH_MEMORY_TYPE=knowledge # knowledge, reflection, both (default: knowledge) DISABLE_REFLECTION_MEMORY=true # default: true

💡 Tip: Copy .env.example to .env and fill in your values:

cp .env.example .env

MCP Server Usage

Cipher can run as an MCP (Model Context Protocol) server, allowing integration with MCP-compatible clients like Claude Desktop, Cursor, Windsurf, and other AI coding assistants.

Quick Setup

To use Cipher as an MCP server in your MCP client configuration:

{ "mcpServers": { "cipher": { "type": "stdio", "command": "cipher", "args": ["--mode", "mcp"], "env": { "MCP_SERVER_MODE": "aggregator", "OPENAI_API_KEY": "your_openai_api_key", "ANTHROPIC_API_KEY": "your_anthropic_api_key" } } } }

📖 See MCP Integration Guide for complete MCP setup and advanced features.

👉 Built‑in tools overview — expand the dropdown below to scan everything at a glance. For full details, see docs/builtin-tools.md 📘.

  • Memory
    • cipher_extract_and_operate_memory: Extracts knowledge and applies ADD/UPDATE/DELETE in one step
    • cipher_memory_search: Semantic search over stored knowledge
    • cipher_store_reasoning_memory: Store high-quality reasoning traces
  • Reasoning (Reflection)
    • cipher_extract_reasoning_steps (internal): Extract structured reasoning steps
    • cipher_evaluate_reasoning (internal): Evaluate reasoning quality and suggest improvements
    • cipher_search_reasoning_patterns: Search reflection memory for patterns
  • Workspace Memory (team)
    • cipher_workspace_search: Search team/project workspace memory
    • cipher_workspace_store: Background capture of team/project signals
  • Knowledge Graph
    • cipher_add_node, cipher_update_node, cipher_delete_node, cipher_add_edge
    • cipher_search_graph, cipher_enhanced_search, cipher_get_neighbors
    • cipher_extract_entities, cipher_query_graph, cipher_relationship_manager
  • System
    • cipher_bash: Execute bash commands (one-off or persistent)

Tutorial Video: Claude Code with Cipher MCP

Watch our comprehensive tutorial on how to integrate Cipher with Claude Code through MCP for enhanced coding assistance with persistent memory:

Click the image above to watch the tutorial on YouTube.

For detailed configuration instructions, see the CLI Coding Agents guide.

Documentation

📚 Complete Documentation

TopicDescription
ConfigurationComplete configuration guide including agent setup, embeddings, and vector stores
LLM ProvidersDetailed setup for OpenAI, Anthropic, AWS, Azure, Qwen, Ollama, LM Studio
Embedding ConfigurationEmbedding providers, fallback logic, and troubleshooting
Vector StoresQdrant, Milvus, In-Memory vector database configurations
Chat HistoryPostgreSQL, SQLite session storage and management
CLI ReferenceComplete command-line interface documentation
MCP IntegrationAdvanced MCP server setup, aggregator mode, and IDE integrations
Workspace MemoryTeam-aware memory system for collaborative development
ExamplesReal-world integration examples and use cases

🚀 Next Steps

For detailed documentation, visit:

Contributing

We welcome contributions! Refer to our Contributing Guide for more details.

Community & Support

cipher is the opensource version of the agentic memory of byterover which is built and maintained by the byterover team.

  • Join our Discord to share projects, ask questions, or just say hi!
  • If you enjoy cipher, please give us a ⭐ on GitHub—it helps a lot!
  • Follow @kevinnguyendn on X

Contributors

Thanks to all these amazing people for contributing to cipher!

Contributors

MseeP.ai Security Assessment Badge

Star History

License

Elastic License 2.0. See LICENSE for full terms.

-
security - not tested
F
license - not found
-
quality - not tested

Cipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS's Kiro, VS Code, and Roo Code through MCP, and coding agents, such as Kimi K2.

  1. Overview
    1. Quick Start 🚀
      1. NPM Package (Recommended for Most Users)
      2. Docker
      3. From Source
      4. CLI Usage 💻
    2. Configuration
      1. Basic Configuration ⚙️
      2. Environment Variables 🔐
    3. MCP Server Usage
      1. Quick Setup
    4. Tutorial Video: Claude Code with Cipher MCP
      1. Documentation
        1. 📚 Complete Documentation
        2. 🚀 Next Steps
      2. Contributing
        1. Community & Support
          1. Contributors
            1. MseeP.ai Security Assessment Badge
              1. Star History
                1. License

                  Related MCP Servers

                  • -
                    security
                    A
                    license
                    -
                    quality
                    A MCP server for Hide – headless IDE for coding agents.
                    Last updated -
                    10
                    Python
                    MIT License
                    • Apple
                    • Linux
                  • -
                    security
                    A
                    license
                    -
                    quality
                    Creates and manages encoded messages using zero-width characters and advanced Unicode steganography techniques, enabling quantum-themed puzzle generation with hidden secrets.
                    Last updated -
                    3
                    JavaScript
                    MIT License
                  • A
                    security
                    A
                    license
                    A
                    quality
                    A fully featured coding agent that uses symbolic operations (enabled by language servers) and works well even in large code bases. Essentially a free to use alternative to Cursor and Windsurf Agents, Cline, Roo Code and others.
                    Last updated -
                    25
                    8,767
                    Python
                    MIT License
                    • Apple
                  • A
                    security
                    A
                    license
                    A
                    quality
                    A coding agent toolkit that transforms LLMs into coding assistants capable of working directly on your codebase with semantic code retrieval and editing tools, providing IDE-like capabilities without requiring API subscriptions.
                    Last updated -
                    33
                    Python
                    MIT License
                    • Linux
                    • Apple

                  View all related MCP servers

                  MCP directory API

                  We provide all the information about MCP servers via our MCP API.

                  curl -X GET 'https://glama.ai/api/mcp/v1/servers/campfirein/cipher'

                  If you have feedback or need assistance with the MCP directory API, please join our Discord server